{"id":"W3015759203","doi":"10.1016/j.eclinm.2020.100332","title":"Evaluating the evidence behind the surrogate measures included in the FDA's table of surrogate endpoints as supporting approval of cancer drugs","year":2020,"lang":"en","type":"article","venue":"EClinicalMedicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":147,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"U.S. Food and Drug Administration; Harvard-MIT Center for Regulatory Science; Arnold Ventures","keywords":"Surrogate endpoint; Medicine; Breast cancer; Clinical endpoint; Internal medicine; Cancer; Oncology; Surrogate data; Clinical trial","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1046603,0.0002269055,0.001356706,0.00009824437,0.000233807,0.00003461429,0.001213254,0.0001292951,0.000569638],"category_scores_gemma":[0.07354777,0.0001439545,0.0001938756,0.0005284611,0.0004775485,0.0002483988,0.0002071793,0.0006544868,0.0001220305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001226756,"about_ca_system_score_gemma":0.000559011,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006653145,"about_ca_topic_score_gemma":0.0007465967,"domain_scores_codex":[0.98867,0.002054799,0.00756253,0.000638498,0.000559408,0.0005147622],"domain_scores_gemma":[0.9751899,0.01770764,0.005788551,0.0009385825,0.0002286036,0.000146728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009824065,0.0005798637,0.7123502,0.002637747,0.0007025059,0.00001084019,0.2163359,0.006747347,0.0005207259,0.02121492,0.02430811,0.01360939],"study_design_scores_gemma":[0.01850056,0.005492278,0.5332241,0.007039073,0.0006592543,0.00003362653,0.1107768,0.2194823,0.001485518,0.05505252,0.04614972,0.002104254],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7548841,0.005795662,0.0001003267,0.2366042,0.000372772,0.001203043,0.00006941596,0.00001499961,0.0009555146],"genre_scores_gemma":[0.9770038,0.000577055,0.0002770213,0.02120176,0.0006443271,0.0001441499,0.000009196817,0.00002597596,0.0001167595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2221196,"threshold_uncertainty_score":0.9999616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7159799799134431,"score_gpt":0.5863906205998416,"score_spread":0.1295893593136015,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}